Tech Meridian ← LIVE FEED
RU

NEWS · CODING · #407

Cohere publishes megakernel serving engine for North Mini Code with faster H100 decoding

Cohere describes a megakernel-based serving engine for its North Mini Code 30B model that runs BF16 on a single NVIDIA H100 and claims 1.25×–1.41× end-to-end speedup over vLLM, with a reported 292 tok/s (62% of SoL) at batch size 1 — about 1.58× faster than vLLM. The system supports production features (continuous batching, paged attention, ragged sequences), an OpenAI-compatible endpoint with tool calling, is implemented as a single CUDA file, and the code is available on GitHub.

KEY POINTS

  1. Cohere describes a megakernel-based serving engine for its North Mini Code 30B model that runs BF16 on a single NVIDIA H100 and claims 1.25×–1.41× end-to-end speedup over vLLM, with a reported 292 tok/s (62% of SoL) at batch size 1 — about 1.58× faster than vLLM.
  2. The system supports production features (continuous batching, paged attention, ragged sequences), an OpenAI-compatible endpoint with tool calling, is implemented as a single CUDA file, and the code is available on GitHub.
  3. It demonstrates that a decode megakernel can be productionized to significantly raise small‑batch LLM throughput on H100s and better approach HBM bandwidth limits.

WHY IT MATTERS

It demonstrates that a decode megakernel can be productionized to significantly raise small‑batch LLM throughput on H100s and better approach HBM bandwidth limits.

SOURCES & TIMELINE

1